Software reliability model predicts component failure rates

This technology is a software package that predicts component failure rates to direct maintenance operations in major industrial networks.

Unmet Need: Accurate prediction of component failures in industrial networks

Component reliability has major impact on continuity of service and maintenance and repair costs in industrial networks such as electrical grids and telecommunication systems. Organizations with large networks of infrastructure components require an effective and accurate statistical analysis solution to direct maintenance operations. There is a need for a systemic model to predict component failures, system outages, and system availability operating.

The Technology: Stochastic model accurately predicts component failures

This system-level reliability model uses a semiparametric stochastic model with machine learning and advanced data cleaning techniques to accurately predict component failures. The system generates vulnerability rankings and mean time between failure (MTBF) estimates for various components of the power grid such as cables, terminators, manholes, and transformers, which can be used to prioritize maintenance work proactively before breakdowns occur. Modules of this technology can be conveniently integrated into corporate management platforms to enhance cost-benefit analyses, maintenance planning, and effort allocation.

The technology has been tested with a Con Edison distribution power feeder, which is a common electric grid component across Manhattan, Queens, and Brooklyn.

Applications:

• Component failure prediction in electric grid networks for power system management
• Component failure prediction in telecommunications equipment
• Modeling principals of stochastic machine learning and data cleaning for health care system management
• Modeling principals of stochastic machine learning and data cleaning in large data systems

Advantages:

• Increase system reliability
• Improved service outage, usage, and profits of the system
• Superior maintenance operations management

Lead Inventor:

Roger N. Anderson, Ph.D.

Patent Information:

Patent Status

Related Publications:

• Rudin C, Waltz D, Anderson RN, Boulanger A, Salleb-Aouissi A, Chow M, Dutta H, Gross PN, Huang B, Ierome S, Isaac DF, Kressner A, Passonneau RJ, Radeva A, Wu L. “Machine learning for the New York City power grid” IEEE Trans Pattern Anal Mach Intell. 2012 Feb, 34(2): 328-345.

Tech Ventures Reference:

• M11-087

• Licensing Contact: Richard Nguyen